Matt Feury
Founder, Distinguished Engineer (2023 - Present), CTO (2017 - 2023) at Flock Safety
Atlanta, Georgia, United States
Summary
👤
Senior🎓
Top SchoolMatt Feury is a seasoned founder and engineering leader with 15 years of experience building music-tech and safety-oriented products from prototype to production. He co-led Flock Safety as Founder and CTO, later serving as Distinguished Engineer, and now runs Green Noise, blending his backgrounds in audio engineering and scalable software. Technically fluent across ML, cloud deployment, and product strategy, he contributed to notable open-source ML tooling like attention-ocr, improving model export and prediction workflows. His career bridges studio floors and data centers—he’s run recording sessions for major artists and implemented production-ready ML systems. Based in Atlanta, he brings a rare combination of creative musical sensibility and disciplined engineering execution.
15 years of coding experience
9 years of employment as a software developer
B.S., Computer Science, Summa Cum Laude, B.S., Computer Science, Summa Cum Laude at Georgia Institute of TechnologyB.S., Audio Engineering Technology, Mathematics, B.S., Audio Engineering Technology, Mathematics at Belmont University
Stackoverflow
11reputation
245reached
0answers
1question
Github Skills (20)
python10
ocr10
image-recognition10
machine-learning10
tensorflow10
ocra10
exporter9
saves9
data-model9
data-export9
mask-rcnn9
mlmodel9
save9
exports9
faster-rcnn9
Programming languages (11)
Github contributions (5)
emedvedev/attention-ocr
Oct 2017 - Oct 2017
A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.
Role in this project:
ML Engineer
ML EngineerContributions:6 commits, 3 PRs, 15 comments in 12 days
Contributions summary:Matt primarily contributed to the model and export functionality within the `attention-ocr` repository. They implemented probability calculations within the model's graph and included this in the export process for the SavedModel. Further work involved refactoring the export process, including building a SavedModel instead of a checkpoint model for prediction. Finally, they addressed an issue related to image preparation and maximum width restrictions.
pythongoogle-cloud-mlimage-recognitionocr-recognitionml-engine
mattfeury/SaucillatorAndroid
Apr 2011 - Jul 2014
A digital synthesizer platform for Android. Currently on the Play Store at version 2.0 Buffalo. A primitive Mac version exists as well.
Contributions:451 commits, 4 PRs, 7 pushes in 3 years 3 months
synthesizermidiprimitiveandroidmac
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.